普通高等学校招生规模的预测方法

近年来,中国普通高等学校招生规模不断扩大,提高了高等教育的入学率,却增加了大学毕业生就业的压力。研究普通高等学校招生规模的预测方法对于合理地制定普通高等学校招生规模,实现高等教育可持续性发展是非常关键的。采用灰色系统方法和神经网络方法,结合1970—2009年全国普通高等学校招生人数的数据资料,建立了普通高等学校招生规模的灰色系统GM(1,1)模型和BP神经网络模型。对2种模型的模拟通过MATLAB平台实现。BP神经网络建模考虑了普通高等学校数、普通高等学校教职工人数、普通高中毕业人数以及国家财政教育经费投入4个影响因素。灰色系统GM(1,1)模型的精度为75.7%;BP神经网络模型的精度为95.4%。通过模拟分析可以得出:BP神经网络方法用于普通高等学校招生规模的预测是可行的。

Predication method for college and university enrollment scale

In recent years,colleges and universities have been expanding enrollment and improving the higher education enrollment rate,resulting in increased pressure on employment for college graduates.Research on prediction methods for enrollment at colleges and universities can be used to develop reasonable enrollment scale and for sustainable higher education development.The gray system and neural network methods are used here to built a gray system GM(1,1) model and a back propagation neural network model using national college enrollment data from 1970 to 2009.Training and simulation of the back propagation neutral network model and the gray system GM(1,1) used MATLAB.The back propagation neutral network model takes into account the number of colleges and universities,the number of college and university faculty,the number of high school graduates and the state financial expenditure on education.The fitting precision of the gray system GM(1,1) model is 75.7% while the fitting precision of the back propagation neutral network model is 95.4%.Thus,the back propagation neutral network model is better for estimating college and university enrollment scale.